Share your thoughts, 1 month free Claude Pro on usSee more

General Language Capability on K&R, IFEval-PT, HumanEval

53.64Average Score

Tucano2-qwen-3.7B-Instruct

Updated 3mo ago

Evaluation Results

Method	Links
Tucano2-qwen-3.7B-Instruct 2026.03		53.64
Jurema-7B 2026.03		53.03
Qwen2.5-3B-Instruct 2026.03		51.71
Qwen3-4B 2026.03		51.36
Gemma-3-Gaia-PT-BR-4b-it 2026.03		49.93
SmolLM3-3B 2026.03		49.54
Llama-3.2-3B-Instruct 2026.03		45.82
Qwen2.5-1.5B-Instruct 2026.03		41.39
Tucano2-qwen-1.5B-Instruct 2026.03		37.54
Qwen3-1.7B 2026.03		36.3
Tucano2-qwen-0.5B-Instruct 2026.03		26.08
Qwen3-0.6B 2026.03		22.21
Llama-3.2-1B-Instruct 2026.03		20.14
Qwen2.5-0.5B-Instruct 2026.03		17.8